TY - GEN
T1 - Comparative study of several novel acoustic features for speaker recognition
AU - Pervouchine, Vladimir
AU - Leedham, Graham
AU - Zhong, Haishan
AU - Cho, David
AU - Li, Haizhou
N1 - Copyright:
Copyright 2009 Elsevier B.V., All rights reserved.
PY - 2008
Y1 - 2008
N2 - Finding good features that represent speaker identity is an important problem in speaker recognition area. Recently a number of novel acoustic features have been proposed for speaker recognition. The researchers use different data sets and sometimes different classifiers to evaluate the features and compare them to the baselines such as MFCC or LPCC. However, due to different experimental conditions direct comparison of those features to each other is difficult or impossible. This paper presents a study of five new recently proposed acoustic features using the same data (NIST 2001 SRE), and the same UBM-GMM classifier. The results are presented as DET curves with equal error ratios indicated. Also, an SVM-based combination of GMM scores produced on different features has been made to determine if the new features carry any complimentary information. The results for different features as well as for their combinations are directly comparable to each other and to those obtained with the baseline MFCC features.
AB - Finding good features that represent speaker identity is an important problem in speaker recognition area. Recently a number of novel acoustic features have been proposed for speaker recognition. The researchers use different data sets and sometimes different classifiers to evaluate the features and compare them to the baselines such as MFCC or LPCC. However, due to different experimental conditions direct comparison of those features to each other is difficult or impossible. This paper presents a study of five new recently proposed acoustic features using the same data (NIST 2001 SRE), and the same UBM-GMM classifier. The results are presented as DET curves with equal error ratios indicated. Also, an SVM-based combination of GMM scores produced on different features has been made to determine if the new features carry any complimentary information. The results for different features as well as for their combinations are directly comparable to each other and to those obtained with the baseline MFCC features.
KW - Feature evaluation
KW - Feature extraction
KW - Speaker recognition
UR - http://www.scopus.com/inward/record.url?scp=70350458906&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:70350458906
SN - 9789898111180
T3 - BIOSIGNALS 2008 - Proceedings of the 1st International Conference on Bio-inspired Systems and Signal Processing
SP - 220
EP - 223
BT - BIOSIGNALS 2008 - Proceedings of the 1st International Conference on Bio-inspired Systems and Signal Processing
T2 - BIOSIGNALS 2008 - 1st International Conference on Bio-inspired Systems and Signal Processing
Y2 - 28 January 2008 through 31 January 2008
ER -